Imports

from utils import print_time_report, print_results, plot_results

Time report

print_time_report()

	hour	min	sec
algo
KNeighborsClassifier	0	13	15
daal4py_KNeighborsClassifier	0	5	15
KNeighborsClassifier_kd_tree	0	5	37
daal4py_KNeighborsClassifier_kd_tree	0	1	34
KMeans	0	21	29
daal4py_KMeans	0	8	26
total	0	55	39

KNeighborsClassifier - Brute Force

print_results(algo="KNeighborsClassifier", versus_lib="daal4py")

plot_results(algo="KNeighborsClassifier", versus_lib="daal4py", group_by_cols=["algorithm", "n_neighbors", "function"], split_hist_by=["n_jobs"])

KNeighborsClassifier - KD Tree

print_results(algo="KNeighborsClassifier_kd_tree", versus_lib="daal4py")

plot_results(algo="KNeighborsClassifier_kd_tree", versus_lib="daal4py", group_by_cols=["algorithm", "n_neighbors", "function"], split_hist_by=["n_jobs"])

KMeans

from utils import _make_dataset
data = _make_dataset('KMeans', 'daal4py', compare_cols=["n_iter"])

data[data["function"] == "fit"].sort_values(["n_iter_sklearn", "n_iter_daal4py"])

	estimator	lib	function	n_samples	n_features	init	max_iter	n_clusters	n_init	tol	adjusted_rand_score	mean_sklearn	stdev_sklearn	n_iter_sklearn	mean_daal4py	stdev_daal4py	n_iter_daal4py	speedup	stdev_speedup
18	KMeans	sklearn	fit	10000	100	k-means++	30	3	1	0.0	NaN	0.5007	0.0048	25.0	0.1339	0.0012	22.0	3.74	4.00
0	KMeans	sklearn	fit	10000	2	k-means++	30	3	1	0.0	NaN	0.0917	0.0237	30.0	0.0041	0.0004	28.0	22.37	59.25
9	KMeans	sklearn	fit	10000	2	random	30	3	1	0.0	NaN	0.0865	0.0228	30.0	0.0083	0.0007	30.0	10.42	32.57
27	KMeans	sklearn	fit	10000	100	random	30	3	1	0.0	NaN	0.0161	0.0006	30.0	0.0037	0.0002	30.0	4.35	3.00
36	KMeans	sklearn	fit	1000000	2	k-means++	30	3	1	0.0	NaN	0.0245	0.0008	30.0	0.0061	0.0005	30.0	4.02	1.60
45	KMeans	sklearn	fit	1000000	2	random	30	3	1	0.0	NaN	0.3591	0.0644	30.0	0.0727	0.0031	30.0	4.94	20.77
54	KMeans	sklearn	fit	1000000	100	k-means++	30	3	1	0.0	NaN	0.1503	0.0058	30.0	0.0248	0.0010	30.0	6.06	5.80
63	KMeans	sklearn	fit	1000000	100	random	30	3	1	0.0	NaN	0.2000	0.0055	30.0	0.0359	0.0008	30.0	5.57	6.87
3	KMeans	sklearn	fit	10000	2	k-means++	30	10	1	0.0	NaN	0.0004	0.0001	NaN	0.0004	0.0003	NaN	1.00	0.33
6	KMeans	sklearn	fit	10000	2	k-means++	30	300	1	0.0	NaN	0.0004	0.0001	NaN	0.0002	0.0001	NaN	2.00	1.00
12	KMeans	sklearn	fit	10000	2	random	30	10	1	0.0	NaN	0.0004	0.0001	NaN	0.0002	0.0001	NaN	2.00	1.00
15	KMeans	sklearn	fit	10000	2	random	30	300	1	0.0	NaN	0.0003	0.0001	NaN	0.0002	0.0001	NaN	1.50	1.00
21	KMeans	sklearn	fit	10000	100	k-means++	30	10	1	0.0	NaN	0.0010	0.0002	NaN	0.0007	0.0002	NaN	1.43	1.00
24	KMeans	sklearn	fit	10000	100	k-means++	30	300	1	0.0	NaN	0.0003	0.0001	NaN	0.0002	0.0001	NaN	1.50	1.00
30	KMeans	sklearn	fit	10000	100	random	30	10	1	0.0	NaN	0.0004	0.0001	NaN	0.0002	0.0001	NaN	2.00	1.00
33	KMeans	sklearn	fit	10000	100	random	30	300	1	0.0	NaN	0.0004	0.0001	NaN	0.0002	0.0001	NaN	2.00	1.00
39	KMeans	sklearn	fit	1000000	2	k-means++	30	10	1	0.0	NaN	0.0004	0.0001	NaN	0.0002	0.0001	NaN	2.00	1.00
42	KMeans	sklearn	fit	1000000	2	k-means++	30	300	1	0.0	NaN	0.0005	0.0005	NaN	0.0002	0.0001	NaN	2.50	5.00
48	KMeans	sklearn	fit	1000000	2	random	30	10	1	0.0	NaN	0.0009	0.0002	NaN	0.0007	0.0001	NaN	1.29	2.00
51	KMeans	sklearn	fit	1000000	2	random	30	300	1	0.0	NaN	0.0004	0.0001	NaN	0.0002	0.0001	NaN	2.00	1.00
57	KMeans	sklearn	fit	1000000	100	k-means++	30	10	1	0.0	NaN	0.0006	0.0001	NaN	0.0003	0.0001	NaN	2.00	1.00
60	KMeans	sklearn	fit	1000000	100	k-means++	30	300	1	0.0	NaN	0.0004	0.0002	NaN	0.0002	0.0001	NaN	2.00	2.00
66	KMeans	sklearn	fit	1000000	100	random	30	10	1	0.0	NaN	0.0007	0.0001	NaN	0.0004	0.0001	NaN	1.75	1.00
69	KMeans	sklearn	fit	1000000	100	random	30	300	1	0.0	NaN	0.0004	0.0002	NaN	0.0002	0.0001	NaN	2.00	2.00

print_results(algo="KMeans", versus_lib="daal4py", compare_cols=["n_iter"])

plot_results(algo="KMeans", versus_lib="daal4py", group_by_cols=["init", "max_iter", "n_clusters", "n_init", "tol", "function"], compare_cols=["n_iter"])